MiniMax M3.1 Flash
Freeminimax/minimax-m3.1-flash1M context · Oct 2026 · 7 upstreamsupstream上游
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it improves across benchmarks, particularly complex agentic tasks, coding and cybersecurity. It is built for multi-step co-work automation, understanding real codebases, fixing bugs and building features, and for visual understanding and creation, including frontend and presentation work. It has a 1M token context window and always-on reasoning with adjustable effort.
- contextngữ cảnh上下文
- 1M
- inputđầu vào输入 / 1M
- $0
- outputđầu ra输出 / 1M
- $0
- routestuyến路由
- 7
- speed, 24htốc độ, 24h速度，24h
- —
Upstreams
7- 1Kilo CodePlatform · freeFreeTPS —TTFT ——
- 2MiniMaxYour key · not addedyour planTPS —TTFT ——
- 3OpenRouterYour key · not addedyour planTPS —TTFT ——
- 4Vercel AI GatewayYour key · not addedyour planTPS —TTFT ——
- 5AIHubMixYour key · not addedyour planTPS —TTFT ——
- 6OpenCode Zen GoYour key · not addedyour planTPS —TTFT ——
- 7ClineYour key · not addedyour planTPS —TTFT ——
- Up
- No traffic
- Down
Try itDùng thử试用
Send a promptGửi một prompt发送提示词
Details
- Owner
- MiniMax
- Kind
- Vision
- Released
- Oct 2026
- Context
- 1M
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
Quick start
curl https://anyrouter.dev/api/v1/chat/completions \ -H "Authorization: Bearer $ANYROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "minimax/minimax-m3.1-flash", "messages": [ { "role": "user", "content": "Say hi in 3 words." } ] }'
GalleryThư viện ảnh图库
Images from the vendorẢnh từ nhà phát hành图片来自厂商
- Multi-step co-work automation across SaaS systems
- Fixing bugs and building features in real codebases
- Code auditing and vulnerability patching
Architecture and licenseKiến trúc và giấy phép架构与许可
StrengthsĐiểm mạnh优势[1],[3]
- Leading-model level on complex agentic tasks, computer use, coding and cybersecurity benchmarks (vendor-reported).
- Output speeds of 200+ tokens per second, with a 170+ median (vendor-reported).
- Vendor reports agentic task cost 70% below M3, at $0.15 input and $0.60 output per 1M tokens.
Known limitsGiới hạn đã biết已知局限[2],[1]
- Always thinks; sending `thinking.type = disabled` returns HTTP 400.
- Model weights are not released yet; the vendor says they will follow later.
API notesGhi chú APIAPI 说明[2]
- Text, image and video input over the OpenAI-compatible Chat Completions API.
- reasoning_effort accepts low, medium, high, xhigh and max; default is max.
- Thinking comes back separately in `reasoning_content` and must be preserved across turns.
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- minimax.io
- DocsTài liệu文档
- platform.minimax.io
- Pricing pageTrang giá价格页
- platform.minimax.io
- Previous versionPhiên bản trước上一版本
- minimax/m3
SourcesNguồn来源
- [1]MiniMax M3.1 Flash: Redefining Agent Performance and Costaccessedtruy cập访问于 2026-10-19
- [2]MiniMax OpenAI API compatible referenceaccessedtruy cập访问于 2026-10-19
- [3]MiniMax pay-as-you-go pricingaccessedtruy cập访问于 2026-10-19
Upstreams and pricingUpstream và giá上游与价格
Share cards9 images
AliasesBí danh别名 (1)
minimax/m3.1-flash
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.